Untangling Dense Knots by Learning Task-Relevant Keypoints

Jennifer Grannen, Priya Sundaresan, Brijen Thananjeyan, Jeffrey Ichnowski, Ashwin Balakrishna, Vainavi Viswanath, Michael Laskey, Joseph Gonzalez, Ken Goldberg

Abstract: Untangling ropes, wires, and cables is a challenging task for robots due to the high-dimensional configuration space, visual homogeneity, self-occlusions, and complex dynamics. We consider dense (t...